检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Zhenyong Liu, Mengxiang Sun, Mingyang Deng, Ruilong Cheng, Peng Niyato, Dusit Chow, Mo-Yuen Chen, Jiming The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550000 China The Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS10 2TN United Kingdom The State Key Laboratory of Industrial Control Technology the College of Control Science and Engineering Zhejiang University Hangzhou310027 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The UM SJTU Joint Institute Shanghai Jiao Tong University Shanghai200240 China

Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid. However, the trustworthiness of ML is a severe issue that must be addressed to accommodate the trend of ML-based smart grid applications (MLsgAPPs). The adversarial distortion injected into the power signal will greatly affect the system’s normal control and operation. Therefore, it is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems. In this paper, we provide a comprehensive review of the recent progress in designing attack and defense methods for MLsgAPPs. Unlike the traditional survey about ML security, this is the first review work about the security of MLsgAPPs that focuses on the characteristics of power systems. We first highlight the specifics for constructing the adversarial attacks on MLsgAPPs. Then, the vulnerability of MLsgAPP is analyzed from both the aspects of the power system and ML model. Afterward, a comprehensive survey is conducted to review and compare existing studies about the adversarial attacks on MLsgAPPs in scenarios of generation, transmission, distribution, and consumption, and the countermeasures are reviewed according to the attacks that they defend against. Finally, the future research directions are discussed on the attacker’s and defender’s side, respectively. We also analyze the potential vulnerability of large language model-based (e.g., ChatGPT) power system applications. Overall, we encourage more researchers to contribute to investigating the adversarial issues of MLsgAPPs. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence Technology in Power System Stability Assessment

引用

Procedia computer Science 2023年 228卷 79-88页

作者： Siyu Xiang Cao zhen Jian Peng Linghao Zhang Zhengguo Pu State Grid Sichuan Electric Power Research Institute Chengdu Sichuan 610095 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611700China College of Computer Science Sichuan University Chengdu 610065 China Anhui Jiyuan Software Co. Ltd. Hefei 230088 China

In order to realize power system stability assessment, the author studies a deep Convolutional neural network algorithm for power system operation stability assessment. Combining short-term simulation with neural network prediction to reduce the time required for transient stability analysis can be used in various simulation analysis scenarios. A deep Convolutional neural network algorithm is used to improve the performance of the security system. A deep Convolutional Neural Network (CNN) is used to construct a multi-layer and multi-column neural network to evaluate the stability of electrical networks. The system significantly improves the efficiency of evaluating specific faults, particularly enhancing the specificity of evaluation judgments, and reducing the additional maintenance workload caused by providing stability warnings for the operation status of faultless power grids. The experimental results indicate that, the system has shown certain advantages in terms of sensitivity to the judgment of various types of faults mentioned above, especially improving the sensitivity to other faults with unknown causes, which is 10.8 percentage points higher than the previous system. The smallest difference in the improvement of sensitivity indicators is the sensitivity to ground faults. The previous system reached 95.4%, while this system increased by 3.9 percentage points to 99.3%. It is proved that the deep CNN is applicable to the task of power system operation stability assessment.

关键词： Deep Convolutional neural network Power system operation Stability assessment Algorithm Innovation

来源：评论

学校读者我要写书评

暂无评论

Hybrid security scheme for a colored image using DNA and chaotic map

Hybrid security scheme for a colored image using DNA and cha...

引用

International Conference on Mathematics, Actuarial Science, computer Science and Statistics (MACS)

作者： Tayyaba Ajaz Humaira Ashraf Ghadah Alwakid Dept. of computer science and software Engineering International Islamic University Islamabad Islamabad Pakistan Department of Computer Science College of computer and information sciences Jouf university Al-Jouf Saudia Arabia

ISBN: (纸本)9781665460729

this paper proposes a color image encryption algorithm based on DNA encoding in conjunction with a 1D logistic map and a high-dimensional chaotic map. The XOR function is used to combine low and high-dimensional chaotic maps, resulting in a cipher image. For image encryption, the paper also proposes a system of confusion and diffusion. Confusion and Diffusion apply to high-dimensional chaotic maps. In a low-dimensional logistic map, the keyspace is smaller, and chaotic sequences are used directly from the chaotic map, which has an impact on the encryption process. Recent image encryption focuses primarily on a gray image scale. We present color image encryption that uses non-RGB color spaces like YCbCr, YIQ, HSV, and L*a*b*. The high connection between RGB color spaces red, green, and blue is commonly used in data storage and handling. RGB color spaces merge Luminance and Chroma channels so color analysis becomes more complex so we use non -RGB spaces. Using the logistic sine map or tent map association, different chaotic systems can be found by random number attacks and dictionary attacks. Gives the security analysis of encryption using DNA encoding and chaotic map and explains that it's vulnerable to plaintext-choice attacks we propose a new and more efficient approach and reduce time complexity then- existing approach and become encryption more secure.

关键词： Image color analysis Chaotic communication DNA Color Mobile communication Encoding Encryption

来源：评论

学校读者我要写书评

暂无评论

Local Learning Joint with the Adaptive Graph for Subspace Representation

Local Learning Joint with the Adaptive Graph for Subspace Re...

引用

International Conference on Intelligent System and Knowledge engineering, ISKE

作者： Yangbo Wang Can Gao Jie Zhou Zhihui Lai College of Computer Science and Software Engineering Shenzhen University Shenzhen Guangdong China

ISBN: (纸本)9781665405546

The technique of local learning that recognizes each sample by its predefined neighbors has been successfully applied in unsupervised learning fields. However, how to determine the proper neighbors of a sample is a challenging problem. Inappropriate selection of neighbors will drastically degrade the performance of local learning methods. In this study, a novel subspace representation method based on local learning joint with the adaptive graph (LLAG) is presented. On the one hand, by exploiting the notion of the adaptive graph and the technique of low-rank constraint, the affinity graph can be constructed iteratively, which prompts the produced subspace to well preserve the local and global structures of the data. On the other hand, the neighbors of samples involved in the local learning are produced adaptively during the optimization process. In this way, more accurate local information that is used to guide the generation of the optimal subspace can be revealed. Extensive experimental results on some benchmark data sets demonstrate the superiority of the proposed method LLAG in comparison with some existing unsupervised learning methods.

关键词： Knowledge engineering Adaptation models Adaptive systems Benchmark testing Intelligent systems Unsupervised learning Optimization

来源：评论

学校读者我要写书评

暂无评论

ENHANCING NEURAL SPOKEN LANGUAGE RECOGNITION: AN EXPLORATION WITH MULTILINGUAL DATASETS

arXiv

引用

arXiv 2025年

作者： Anidjar, Or Haim Yozevitch, Roi Department of Computer Software & Engineering Ariel University Golan Heights 1 Ariel4077625 Israel Department of Electrical Engineering Ariel University Golan Heights 1 Ariel4077625 Israel Faculty of Computer Science College of Management Elie Wiesel 2 Rishon LeTsiyon7579806 Israel Ariel Cyber Innovation Center Ariel University Golan Heights 1 Ariel4077625 Israel

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized pooling layer. We utilized a broad dataset range from Common-Voice, targeting ten languages across Indo-European, Semitic, and East Asian families. The major innovation involved optimizing the architecture of Time Delay Neural Networks. We introduced additional layers and restructured these networks into a funnel shape, enhancing their ability to process complex linguistic patterns. A rigorous grid search determined the optimal settings for these networks, significantly boosting their efficiency in language pattern recognition from audio samples. The model underwent extensive training, including a phase with augmented data, to refine its capabilities. The culmination of these efforts is a highly accurate system, achieving a 97% accuracy rate in language recognition. This advancement represents a notable contribution to artificial intelligence, specifically in improving the accuracy and efficiency of language processing systems, a critical aspect in the engineering of advanced speech recognition technologies. Copyright © 2025, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Current-Constrained Finite-Time control Scheme for Speed Regulation of PMSM Systems With Unmatched Disturbances

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 16877-16887页

作者： Huiming Wang Zhize Zhang Yingjie Luo Junxiao Wang Jiankun Sun Yunda Yan Xianlun Tang Chongqing Key Laboratory of Complex Systems and Autonomous Control Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China College of Information Engineering Zhejiang University of Technology Hangzhou China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China Department of Computer Science University College London London U.K.

The article investigates the speed regulation of permanent magnet synchronous motor (PMSM) systems. Existing control methods of the non-cascade structure suffer from the drawbacks of unsatisfactory anti-disturbance performance and slow convergence rate when the system is affected by disturbances, especially unmatched disturbances. Meanwhile, the requirements of current constraint and fast dynamics cannot be effectively balanced in the single-loop structure of speed and current using traditional control methods such as the PID controller. Because large transient currents induced by fast dynamics may damage the hardware of the system. Therefore, a current-constrained finite-time control approach is proposed. Specifically, a robust finite-time control scheme is developed with the assistance of the improved finite-time observer technique. The proposed method is capable of actively suppressing both matched and unmatched disturbances in non-cascade control systems. Simultaneously, an effective penalty mechanism is established to incorporate a specific gain function into the designed controller. This approach restricts the q-axis current to a predefined safe range without solving an optimization problem. Finally, comparative experiment results indicate that the newly proposed finite-time control method outperforms the baseline control methods in terms of disturbance rejection, convergence rate, and current constraint. Note to Practitioners—This paper addresses practical challenges in controlling permanent magnet synchronous motor (PMSM) systems, such as ensuring robust disturbance rejection while limiting transient currents to protect the hardware. Traditional methods often fail to balance fast dynamics with current constraints, leading to inefficiencies and potential damage. To tackle these issues, the proposed finite-time control approach introduces a practical solution that achieves robust disturbance rejection while ensuring that transient currents remain within safe o

关键词： Convergence Observers control systems Automation Transient analysis Asymptotic stability Stability analysis Regulation Permanent magnet motors Optimization

来源：评论

学校读者我要写书评

暂无评论

QoS Optimization via Computation Offloading in Metaverse Environment

QoS Optimization via Computation Offloading in Metaverse Env...

引用

IEEE International Conference on Web Services (ICWS)

作者： Zhiyuan Ge Pengcheng Zhang Huiying Jin Hai Dong Shunhui Ji Jiajia Li Qi Wang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

The emergence of the metaverse signifies a paradigm shift in Internet technology, offering a comprehensive virtual social platform spanning various domains such as social interaction, gaming, healthcare, and tourism. This new era of the metaverse is facilitated by advancements in next-generation digital technologies including edge computing, artificial intelligence, virtual reality, augmented reality, and blockchain. In the metaverse, the quantity and variety of services requested by users may surpass those in other environments, and existing work cannot be applied to metaverse QoS (Quality of Service) optimization. To address this problem, this paper proposes Meta-PPO, an optimization method for enhancing the QoS of metaverse services using reinforcement learning. Firstly, metaverse services are categorized into virtual scene services and meta-services, providing a comprehensive framework for analysis. Secondly, Meta-PPO, based on the proximal policy optimization algorithm, is introduced to optimize the QoS of metaverse services. This method effectively balances the objectives of minimizing average delay and maximizing resource utilization of mobile devices by making informed offloading decisions for the identified service categories. Simulation results demonstrate the superiority of the proposed method over existing techniques, showcasing its suitability and effectiveness for enhancing the QoS of metaverse service.

关键词： Metaverse Web services Simulation Optimization methods Quality of service Reinforcement learning Mobile handsets Delays Resource management Object recognition

来源：评论

学校读者我要写书评

暂无评论

Deep learning based DeepFake video detection

Deep learning based DeepFake video detection

引用

Smart Computing and Application (ICSCA), International Conference on

作者： Sarra Guefrachi Marwa Ben Jabra Naif A. Alsharabi Mohamed Tahar Ben Othman Yasser O. Alharabi Abdulsalam Alkholidi Habib Hammam Faculty of Engineering Université de Moncton) Moncton NB Canada Spectrum of Knowledge Production & Skills Development Sfax Tunisia Computer Engineering University of Ha'il Computer Science Amran University Yemen Ha'il KSA Department of Computer Science College of Computer) Qassim University Buraydah Saudi Arabia line Computer Science and Information College of computer sc. & engneering Ha'il University Ha'il KSA College Department of Software Engineering Canadian Institute of Technology Tirana Canada International Institute of Technology and Management Commune d'Akanda Libreville BP Ga-bon Dept of Electrical and Electronic Eng. Science School of Electrical Engineering University of Johannes-burg Tirana Canada

Recent advances in DeepFake face-swapping technology have made it simple to create fake videos that appear remarkably real. Since it has been employed in numerous instances for deceit, extortion, and the falsification of facts, its widespread use has generated a huge social, security, and political risk. Its use on websites and social media has become more widespread. Detecting this crime is becoming more and more important due to the potential harm false videos may inflict on a global scale. This research offers a method for building a deep learning model that really can tell the difference between authentic and false videos. The article describes how to create new models based on the VGG16 neural network, a previously created neural network that does image categorization, using transfer learning in the computer vision field. Deep learning is still becoming better at both producing and spotting DeepFakes. DeepFake detection algorithms are developed using dated public datasets, and as a result, they may become obsolete with time. and require continual updating. The research findings are encouraging, and our results reached an accuracy rate of over 90%.

关键词： Deep learning Deepfakes computer vision Social networking (online) Computational modeling Neural networks Transfer learning

来源：评论

学校读者我要写书评

暂无评论

RSA-1024 Cryptography on Artix-7 FPGA: Medical Imaging Application

RSA-1024 Cryptography on Artix-7 FPGA: Medical Imaging Appli...

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Ridha Ghayoula Wided Amara Amor Smida Jaouhar Fattahi Mohamed I. Waly Sahbi Bahroun Issam El Gmati Faculty of Engineering University of Moncton New Brunswick Canada SysCom Laboratory ENIT University of Tunis El Manar Tunis Tunisia College of Applied Medical Sciences Majmaah University Majmaah KSA Department of Computer Science && Software Engineering Laval University Quebec Canada Institut Superieur d’Informatique University of Tunis El Manar Tunis Tunisia College of Engineering Umm Al Qura University Umm Al Qura KSA

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

In the domain of medical imaging, ensuring the security of confidential patient data stands as a paramount concern. The imperative for robust encryption to safeguard medical images against unauthorized access has driven the widespread adoption of the RSA algorithm, celebrated for its efficacy in data security assurance. This study specifically centers on the deployment of RSA-1024 cryptography on an Artix-7 FPGA, targeting applications in medical imaging. Acknowledging the demand for heightened security and accelerated processing, we have engineered RSA crypto-accelerators as hardware implementations of the RSA algorithm. We present a comprehensive methodology for implementing the 1024-bit RSA encryption/decryption algorithm, leveraging the square and multiply technique for modular exponentiation. Our algorithms are meticulously instantiated through VHDL code, tailored for execution on the Artix-7 xc7a35tcsg324-1 FPGA manufactured by Xilinx. Rigorous testing using the Vivado 2022.2 tool validates the functionality and dependability of our design. This research underscores the pivotal role of advanced cryptographic methodologies in safeguarding medical images and underscores the strides made in FPGA-based security solutions.

关键词： VHDL Codes Scalability Refining Reliability engineering Encryption Security

来源：评论

学校读者我要写书评

暂无评论

A Self-play and Sentiment-Emphasized Comment Integration Framework Based on Deep Q-Learning in a Crowdsourcing Scenario : Extended Abstract

A Self-play and Sentiment-Emphasized Comment Integration Fra...

引用

International Conference on Data engineering

作者： Huan Rong Victor S. Sheng Tinghuai Ma Yang Zhou Mznah Al-Rodhaan School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing China Department of Computer Science Texas Tech University Lubbock USA School of Computer & Software Nanjing University of Information Science & Technology Nanjing China Department of Computer Science & Software Engineering Auburn University Auburn USA College of Computer & Information Sciences King Saud University Riyadh Kingdom of Saudi Arabia

Crowdsourcing is a sourcing model where individuals or organizations obtain goods and services from a large, relatively open and often rapidly evolving group of internet users. The most common way that crowdsourcing can facilitate machine learning is to annotate instances with labels [1] . However, the same instance may have inconsistent class labels, in the eyes of various annotators. Therefore, current efforts in crowdsourcing mainly focus on the truth inference or label integration, to remove inconsistent labels or to alleviate biased labeling. In turn, instances with the integrated labels could facilitate the training on machine learning models. The future direction of crowdsourcing is to apply more fine-grained truth inference methods to different application domains [2] . Consequently, we evolve toward another challenging problem of comment integration. That is, how can we integrate or summarize the core opinions of multiple product comments obtained from users, rather than the discrete labels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：